Created some helper scripts, for extracting flags and tags from LEXC …

…files, and aggregating multiple LEC files into a single one.

src/fst/morphology/incoming/resplit/aggregate-lexc.sh

@@ -0,0 +1,3 @@
+#!/bin/sh
+
+cat root.lexc noun_prefixes.lexc noun_stems.lexc noun_suffixes.lexc verb_prefixes.lexc prevn.lexc verb_stems.lexc verb_suffixes.lexc > lexicon.lexc

src/fst/morphology/incoming/resplit/extract-flags.sh

@@ -0,0 +1,18 @@
+#!/bin/sh
+
+# extract-flags.sh (LEXC)
+
+# Usage:
+#    cat lexicon.lexc | ./extract-flags.sh
+
+gawk '{
+ sub("!.*$","");
+ while(match($0,"@[^@]+@",f)!=0)
+      {
+        sub(f[0],""); flags[f[0]]++;
+      }
+}
+END {
+  PROCINFO["sorted_in"]="@ind_str_asc";
+  for(ff in flags) print ff;
+}'

src/fst/morphology/incoming/resplit/extract-tags.sh

@@ -0,0 +1,20 @@
+#!/bin/sh
+
+# extract-flags.sh (LEXC)
+
+# Usage:
+#    cat lexicon.lexc | ./extract-flags.sh
+
+gawk '{
+ sub("!.*$","");
+ while(match($0,"\\+[^\\+]+",f)!=0)
+      {
+        tag=f[0];
+        gsub("\\+","\\+",tag);
+        sub(tag,""); tags[tag]++;
+      }
+}
+END {
+  PROCINFO["sorted_in"]="@ind_str_asc";
+  for(tt in tags) print tt;
+}'